superclawd@0.1.45
Claude Code, supercharged — your team's standards, every session. The superclawd CLI loads your workspace's skills, agents, commands, workflows, and live directives into Claude Code as a plugin.
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThis is a guarded, first-party agent-extension capability with remote policy content, so it warrants a warning. The static malicious label is not supported by concrete install-time or unconsented attack behavior.
Decision evidence
public snapshot- Explicit CLI execution creates a Claude Code plugin with an MCP server and live directives.
- The hook helper requests remote foundational prompt text and includes a repository fingerprint.
- The package embeds an always-effective operating-manual prompt for the launched agent.
- package.json has no preinstall, install, or postinstall hook; prepublishOnly only builds for publishing.
- The extension is generated and launched through the user-invoked superclawd CLI.
- Observed network hosts and credential use are package-aligned SuperClawd service endpoints; no unrelated exfiltration receiver was found.
Source & flagged code
7 flaggedSource sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/index.jsView on unpkg · L2Findings
Affected versions and remediation
This report applies to superclawd@0.1.45.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.45 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.